Browser automation

6,874 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

BanmaXM/operate-ui-by-screenshot

Skill Claude CodeCodex

Operate desktop apps and websites through structured browser interfaces, DOM/HTML inspection, UI Automation, screenshots, visible UI state, clipboard paste, safe clicks, verification screenshots, and reusable app/site operation notes. Use when Codex needs to control or inspect a GUI/web app, click buttons, open…

not rated 53 2mo ago A 118 tokens original MIT

chrome-tools

362

nicholmikey/chrome-tools-MCP

MCP server Claude CodeCodexCursor +2

MCP server for Chrome DevTools Protocol integration - control Chrome tabs, execute JavaScript, capture screenshots, and monitor network traffic. Runs locally from the @nicholmikey/chrome-tools npm package.

not rated 53 1y ago A tokens not measured original MIT

browser-game

363

DanMcInerney/orchflows

Skill Claude Code

Turn an incomplete browser-game brief into evidence-bound checkpoints and standard-stamped successor delivery.

not rated 53 +1 changed yesterday A 20 tokens original MIT

ufo-browser

364

VictorSimon1/ufo-browser

Skill Codex

UFO-Browser is a high-performance local Chromium browser built for AI Agents and people to work in isolated Task Spaces while reusing browser login state. Use this skill whenever a task requires opening or navigating websites, filling forms, clicking controls, taking screenshots, extracting page data, testing web…

not rated 52 18d ago A 101 tokens

domshell

366

apireno/DOMShell

MCP server Claude CodeCodexCursor +2

Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent. Runs locally from the @apireno/domshell npm package.

not rated 52 22d ago A tokens not measured original MIT

agent-browser

367

eddie-292/grapwork

Skill Claude Code

Browser automation for AI agents. Triggers on requests to open websites, fill forms, click buttons, take screenshots, scrape data, test web apps, login to sites, or automate browser tasks.

not rated 51 4mo ago A 42 tokens original MIT

jsrpc-mitm-auto

368

hzhsec/AICryptoProxy

Skill Claude CodeCodex

A bridge between browser JavaScript and mitmproxy that lets browser functions handle encryption and decryption. JSRPC connects the proxy to those JavaScript functions, while mitmproxy handles network traffic.

not rated 51 3mo ago A 59 tokens

mukul975/mcp-windows-automation

MCP server Claude CodeCodexCursor +2

MCP server "unified-windows-server" as configured in mukul975/mcp-windows-automation. Runs D:\MCP\mcpwindows\unified_server.py with python. Needs 1 environment variable to run.

not rated 51 +1 3mo ago A tokens not measured original MIT

real-browser-mcp

371

ofershap/real-browser-mcp

Cursor rule Cursor

Instructions for using Real Browser MCP to control the user's actual browser.

not rated 50 +1 6d ago A 1,661 tokens original MIT

linkedin

372

Linked-API/linkedin-skills

Skill Claude CodeCodex

General-purpose LinkedIn automation – fetch profiles, search people and companies, send messages, manage connections, create posts, and more. Use when the user wants to interact with LinkedIn.

not rated 50 +4 24d ago A 39 tokens copy · 91% MIT

moltbrowser

373

Joakim-Sael/moltbrowser

Skill Claude Code

Browser automation with WebMCP Hub integration. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information — with automatic per-site tool discovery from the community hub.

not rated 50 5mo ago A 48 tokens original Apache-2.0

hjdhnx/drpy-node-skill

Skill Claude CodeCodex needs its repo

An archived workflow for creating a drpy-node source, which is a JavaScript rule file that collects content from a website. It covers analysing the site, choosing a template, writing rules, and basic checks.

not rated 49 +1 today A 104 tokens original MIT

workbuddy-checkin

375

GitOfUser/workbuddy-checkin

Skill Claude CodeCodex

A browser-automation skill that completes a daily check-in on WorkBuddy using Playwright. Playwright is a tool for controlling a web browser through code.

not rated 49 2mo ago A 116 tokens

perplexity-comet-mcp

376

RapierCraft/Perplexity-Comet-MCP

MCP server Claude CodeCodexCursor +2

Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management. Runs locally from the perplexity-comet-mcp npm package. Needs 2 environment variables to run.

not rated 48 +1 2mo ago A tokens not measured original MIT

cloak-fetch

377

Agents365-ai/cloakFetch

Skill Claude CodeCodex

Use as a fallback when a web page won't load via WebFetch, curl, or any HTTP client because it's behind anti-bot protection — Cloudflare, DataDome, Akamai Bot Manager, PerimeterX/HUMAN, Imperva/Incapsula, F5/Distil, Kasada, AWS WAF, Sucuri, or generic WAF/CDN screening — and returns 403/429/"Just a moment"/"Access…

not rated 48 3mo ago A 128 tokens original MIT

bb-browser

378

liangdabiao/fetch-everything

MCP server Claude CodeCodexCursor +2

Your browser is the API. CLI for AI agents to control Chrome with your login state. Runs locally from the bb-browser npm package.

not rated 48 +1 5mo ago A tokens not measured

ai-browser

379

AI-XiaoDao/ai-browser-mcp

MCP server Claude CodeCodexCursor +2

MCP server "ai-browser" as configured in AI-XiaoDao/ai-browser-mcp. Runs CEFbro/AI-Fbowser-Mcp/mcp_bridge.js with node. Needs 3 environment variables to run.

not rated 48 +1 8d ago A tokens not measured original MIT

agent-browser

380

skeletorflet/opencode-supreme-setup

Skill Claude Code

Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking buttons, taking screenshots, extracting page data, testing web apps, dogfooding Open Design previews, QA, bug hunts, or reviewing app quality. Prefer local Open Design…

not rated 47 3mo ago A 81 tokens original MIT

gsd-browser

381

open-gsd/gsd-browser

Skill Claude Code

Open GSD native browser automation for AI agents. Use gsd-browser when the user needs real Chrome/Chromium control: navigate pages, inspect localhost, click, type, fill forms, take screenshots, capture stable snapshot refs, run assertions and waits, extract structured data, compare visual diffs, inspect…

not rated 47 yesterday A 180 tokens original Apache-2.0

vindicate

382

OpenEvident/vindicate

Skill Claude CodeCodex

Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…

not rated 46 yesterday A 77 tokens original Apache-2.0

crawl4ai

383

brettdavies/crawl4ai-skill

Skill Claude Code

Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (crwl CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai…

not rated 46 2mo ago A 132 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: